AI researcher · Notre Dame

Building agents that
learn, reason & use tools.

I’m Hy Dang, a Ph.D. candidate in Computer Science and Engineering at the University of Notre Dame. I work in the DM2 Lab, advised by Prof. Meng Jiang. My research focuses on reliable and self-improving LLM agents: how they use and create tools, learn from experience, and tackle complex reasoning tasks.

A journey in the making.

Research, industry, and milestones during my Ph.D.

  1. JUN–SEP 2026
    OracleApplied Scientist Intern · Skill evolution for LLM agents Industry

    During my internship in Redwood City, I developed an agentic AI framework for skill evolution, enabling LLM agents to construct, refine, and reuse task-specific skills for complex reasoning and decision-making.

  2. AUG 2026
    OpenToolsEMNLP 2026 Demo Track · Community-driven tool-using agents Research

    1st-author paper got accepted to EMNLP 2026 Demo Track: Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents. OpenTools addresses both tool-use accuracy and the intrinsic reliability of tools. Thank you to all collaborators!

    Explore OpenTools
  3. JUN 2026
    Ph.D. candidacyTowards Reliable Tool-Augmented Agentic AI Frameworks Education

    I passed my Oral Candidacy Exam at Notre Dame. Thank you to my committee: Dr. Meng Jiang, Dr. Toby Li, Dr. Zhi Zheng, and Dr. Avi Sil.

  4. APR 2026
    Rideshare disparitiesCSCW 2026 · Earning and work patterns in Chicago Research

    1st-author paper got accepted to CSCW 2026: Uncovering Disparities in Rideshare Drivers’ Earning and Work Patterns: A Case Study of Chicago. Thank you to all collaborators!

    Read the paper
  5. AUG 2025
    Guided function callingEMNLP 2025 · Work from my Amazon internship Research

    1st-author paper got accepted to EMNLP 2025 Main: Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates. This work was completed during my Amazon internship. Thank you to all collaborators!

    Explore the project
  6. MAY 2025
    DYDECOMPACL 2025 · Optimizing decomposition for claim verification Research

    Optimizing Decomposition for Optimal Claim Verification, with Yining Lu, Noah Ziems, and Meng Jiang, was accepted to ACL 2025 Main.

    Read the paper
  7. SEP 2024
    Amazon RufusApplied Scientist Intern · September 2024–May 2025 Industry

    I worked with Team Rufus in Palo Alto on improving the tool-use and function-calling capabilities of LLMs. My mentors were Dr. Tianyi Liu, Dr. Zhuofeng Wu, Jingfeng Yang, and Dr. Haoming Jiang.

  8. MAY 2023
    Community recommendationCODI at ACL 2023 · Mental health discourse Research

    Co-1st-author paper got accepted to the 4th Workshop on Computational Approaches to Discourse at ACL 2023: Embedding Mental Health Discourse for Community Recommendation. Thank you to all collaborators!

    Explore the project
  9. AUG 2022
    University of Notre DamePh.D. in Computer Science and Engineering · DM2 Lab Education

    I began my Ph.D. in Computer Science and Engineering at the University of Notre Dame, advised by Prof. Meng Jiang in the DM2 Lab.

Selected research.

Tools, reasoning, and the systems we build around them.

EMNLP 2026 · Demo Track

Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents

CSCW 2026

Uncovering Disparities in Rideshare Drivers’ Earning and Work Patterns: A Case Study of Chicago

EMNLP 2025

Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates

ACL 2025

Optimizing Decomposition for Optimal Claim Verification

CODI · ACL 2023

Embedding Mental Health Discourse for Community Recommendation

LLM Symposium · IJCAI 2023

A Quantitative Review on Language Model Efficiency Research